Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

REA

AI overview

Sign in and the AI will write an overview from our coverage.

Headlines · 7

  1. AI reverse engineering sweeps GitHub as REA tops trending with 120k stars

    Over the past week, GitHub's trending list has been dominated by AI reverse-engineering projects. According to the report, REA (Reverse Engineer Anything) connects professional tools such as Ghidra, Hopper and IDA to coding agents via the MCP protocol, letting users describe what they want to Claude and have it disassemble a program or even rebuild the feature itself; the project reportedly passed 120,000 stars and hit the top of the trending chart in under a week. The article also says former Square engineer Brandon Thomas used Claude Opus 5.5 and Rust to recreate seven Adobe apps, and that his ArtCraft team then rewrote Microsoft Word from public specifications as WordCraft, which reached 6,000+ stars within five days of appearing on GitHub.

    36氪 人工智能 · 🔥 6
  2. AI reverse-engineering tool REA reportedly hits 200k GitHub stars in 9 days

    DoNews reports that REA, an AI-powered reverse-engineering tool, collected 200,000 GitHub stars within nine days of launching and has allegedly been used to crack multiple AAA games. The report offers no technical details, maintainer information or description of how the tool works. Both the star count and the cracking claims come from a single source and have not been independently verified.

    DoNews · 🔥 4
  3. REA tops GitHub as AI takes over reverse engineering

    The open-source project REA (Reverse Engineer Anything) plugs disassembly tools such as Ghidra, IDA and Hopper into AI coding agents like Claude Code, Codex and Cursor through MCP, so a user can ask an agent to investigate how an app's feature works and show the evidence. Star History counted 78,800 new stars for REA in the week of Oct 4–10, first among GitHub projects that week, with its total nearing 100,000 when the piece was written; a homepage case traces a DX-Ball sound call to the function that computes left and right channels, reconstructs it in C, passes 3,205 tests and compiles to 63 bytes identical to the original. Elias Bachaalany, co-author of a reverse-engineering textbook, dismissed it with the single word 'hype', and in the same week developer Brandon Thomas released ArtCraft, seven free Rust programs built with Claude Opus 5.5 that target Adobe Photoshop, Premiere and others; PhotoCraft gained 42,900 stars in a week, but users reported broken PSD files containing Smart Objects, crashes when importing many clips, and only 5 of 30 filter-effect tests matching.

    36氪 人工智能 · 🔥 0
  4. REA tops 110K stars in a week as AI reverse-engineering wave stirs legal debate

    REA (Reverse Engineer Anything) connects reverse-engineering tools such as Ghidra, IDA and JADX to coding agents like Claude Code and Codex through MCP, so a single prompt makes an agent inspect a binary or app package and return findings with evidence. Citing Star History data, the article says the project went from under 10,000 stars on October 6 to more than 110,000 on October 12 — roughly 100,000 stars in six days. It notes that open-source projects wiring AI into reverse-engineering tools, such as GhidraMCP and IDA Pro MCP, already existed, that several reverse-engineering experts call the hype overblown, and that sending decompiled output to model providers plus anti-decompilation clauses in user agreements can raise trade-secret, copyright and contract risks.

    36氪 人工智能 · 🔥 0
  5. REA: AI-powered reverse engineering project fuels debate over rebuilding software

    An analysis piece examines the GitHub open-source project REA (Reverse Engineer Anything), whose star count passed 110,000 as of October 12. Developer Brandon Thomas says he used AI to build seven Adobe alternatives and declared "Software is over"; REA connects to analysis tools such as Ghidra, Hopper and IDA, handles JavaScript, Electron apps and websites, and can work with agents like Claude Code and Codex to trace data flows and rewrite code. Cited cases include an Aegis verification-code reimplementation whose output matched the original in 133 tests, and a DX-Ball sound function that matched across 3,205 tests and produced 63 bytes of matching machine code under a specified old compiler. The article also covers browser ports of games such as Halo and GTA: Vice City, and VibeOffice, which brings an Office 2003-style interface to the browser.

    虎嗅 AI · 🔥 0
  6. REA plugs reverse-engineering tools into Claude Code, Codex and Cursor

    An open-source MCP service called REA (Reverse Engineer Anything) has topped GitHub Trending, with the cited post claiming a one-day gain of 25,784 stars and more than 60,000 in total. REA connects disassembly and reverse-engineering tools to AI coding agents such as Claude Code, Codex and Cursor through a single install command (npx rea-agents setup), letting an agent trace code while a human verifies the evidence; it covers native binaries, Electron apps, .NET programs, Android APKs, firmware, websites and packet captures. The article cautions that the project's public demos use small, curated functions (many only 63 bytes), and that a Quarkslab test of Claude Opus 5 in a sandbox against hardened AArch64 binaries broke no sample, so obfuscation still raises attacker costs and the real moat of apps like WeChat sits on the server side.

    虎嗅 AI · 🔥 0
  7. REA hits 120K GitHub stars as agents learn to reverse-engineer any app

    REA (Reverse Engineer Anything) is an MIT-licensed TypeScript project by developer morluto that puts tools such as Ghidra, Hopper and IDA behind an MCP server so coding agents like Claude Code, Codex, Cursor and Gemini CLI can investigate software without source code. 36Kr reported the repository had about 120,000 GitHub stars by Oct 12, with growth surging after a 4.1.0 release on Oct 7 added mobile-app analysis, though other reports put the count at roughly 50,000–80,000. Documented examples include recovering a DX-Ball sound-panning routine as C code that passed 3,205 original x86 test cases, and tracing Notion's clipboard bridge; the community has since pointed it at Adobe and Google apps plus WeChat, Alipay and Douyin, though 36Kr notes those apps' core logic runs server-side behind packing, obfuscation and risk-control defenses.

    开源中国 · 🔥 0

Experience and discussion from the community

Share my REA experienceAsk about REA

Nobody has shared their experience with REA yet.